본문 바로가기
KERD
논문KCI 등재

한국어-중국어 신경망 기계 번역에 대한 수동평가: 사회과학과 기술과학 카테고리에서 나타나는 구글 번역(GNMT)과 파파고(N2MT)의 정확도

Evaluation of Korean-Chinese Neural Network Machine Translation-Differences between Google Translation (GNMT) and Papago (N2MT) in the Fields of Social Science and Technical Science

0

조회

0

다운로드

10

인용

0

참고문헌

키워드

주제분류통역번역학

초록

This study conducted machine translation evaluation using GNMT and N2MT machine translation programs. The subject area is articles in the fields of social science and technical science. The evaluation items at the level of words, phrases, sentences, and text were presented, and the accuracy and fluency of Korean-Chinese machine translation were evaluated and analyzed in a 10-point scale. This paper categorizes the types of errors repeatedly appearing in machine translation into four and applied them as top evaluation items. Evaluation models were presented by supplementing and revising several evaluation models presented in previous studies. We will apply this to the text to be analyzed and examine the accuracy and difference of GNMT and N2MT. The analysis results are as follows. First, as a result of field evaluation, GNMT translated social science and technical science with almost the same accuracy. On the other hand, N2MT was significantly less accurate in translating technical science than in translating social science. Second, there were differences among error types, which were observed in translations of both GNMT and N2MT. The highest number of errors occurred at the word level for both neural network translators.

Abstract

This study conducted machine translation evaluation using GNMT and N2MT machine translation programs. The subject area is articles in the fields of social science and technical science. The evaluation items at the level of words, phrases, sentences, and text were presented, and the accuracy and fluency of Korean-Chinese machine translation were evaluated and analyzed in a 10-point scale. This paper categorizes the types of errors repeatedly appearing in machine translation into four and applied them as top evaluation items. Evaluation models were presented by supplementing and revising several evaluation models presented in previous studies. We will apply this to the text to be analyzed and examine the accuracy and difference of GNMT and N2MT. The analysis results are as follows. First, as a result of field evaluation, GNMT translated social science and technical science with almost the same accuracy. On the other hand, N2MT was significantly less accurate in translating technical science than in translating social science. Second, there were differences among error types, which were observed in translations of both GNMT and N2MT. The highest number of errors occurred at the word level for both neural network translators.

참고문헌 (23)

  1. 강병규, "신경망 기계번역의 작동 원리와 번역의 정확률 - 중한 번역을 실례로", 중어중문학, (73), pp.253~295 (2018), 한국중어중문학회[DOI]
  2. 공수, "기계번역 프로그램 품질에 대한 사용자 평가와 사용자의 L2 수준 간 상관관계 고찰 -한중 언어 쌍을 중심으로-", 통역과 번역, 21(3), pp.1~29 (2019), 한국통역번역학회[DOI]
  3. 곽중철, "포스트에디팅 측정지표를 통한 기계번역 오류 유형화 연구", 통번역학연구, 22(1), pp.1~25 (2018), 통번역연구소[DOI]
  4. 권도경, "2018년 인공신경망 기계번역의 중한 번역 현황 - 구글 번역과 네이버 파파고를 중심으로", 중국문학, 98, pp.233~266 (2019), 한국중국어문학회[DOI]
  5. 기유미, "한중 기계번역 오류의 문형별 비교분석-네이버 파파고 번역기와 구글 번역기를 중심으로-", 중국연구, 74, pp.3~32 (2018), 중국연구소[DOI]
  6. 김혜림, "기계번역과 인간번역의 문체 비교: 신문사설 한중번역을 중심으로", 통번역학연구, 24(1), pp.21~47 (2020), 통번역연구소[DOI]
  7. 남철진, "中韓(韓中) 번역을 통해 본 구글번역(GNMT)의 문제", 중국과 중국학, 34, pp.1~27 (2018), 중국연구센터[DOI]
  8. 송연석, "기계번역 담론에 대한 비판적 고찰", 번역학연구, 19(1), pp.119~145 (2018), 한국번역학회[DOI]
  9. 이재환, "Subword 유닛과 역 번역을 이용한 한국어-영어 신경망 기계 번역", 석사, pp.2019
  10. 이주리애, "인공신경망 기계 번역의 한일", 일한 번역 품질에 대한 예비연구-품질향상 검토와 교열코드 적용-, 2018, pp.20(1), 43~71[DOI]
  11. 이준호, "신경망기계번역의 객관적 평가를 위한 예비연구: 자동평가와 수동평가의 균형점", 통번역학연구, 23(3), pp.171~202 (2019), 통번역연구소[DOI]
  12. 정혜연, "번역의 자동평가: 기계번역 평가를 인간번역 평가에 적용해보기", 통번역학연구, 22(4), pp.265~287 (2018), 통번역연구소[DOI]
  13. 지인영, "신경망기계번역 기술 진화와 번역품질 분석", 통번역학연구, 24(3), pp.191~223 (2020), 통번역연구소[DOI]
  14. 최효은, "특허 기계번역 결과물의 평가 - KIPRIS의 무료 한영 기계번역을 중심으로", 통역과 번역, 19(1), pp.139~178 (2017), 한국통역번역학회[DOI]
  15. 황은하, "언어학적 지식에 기반한 한중 뉴스 표제의 기계번역", 번역학연구, 15(5), pp.333~362 (2014), 한국번역학회[DOI]
  16. Callison-Burch, C., "Re-evaluating the Role of Bleu in Machine Translation Research", pp.249~256 (2006)
  17. Hampshire, S., "Translation and the Internet:evaluating the quality of free online machine translators", Quaderns: revista de traducci, (17), pp.197~209 (2010)
  18. Koehn, P., "Six Challenges for Neural Machine Translation", Association for Computational Linguistics, pp.28~29 (2017)
  19. Knowles, R., "A user study of neural interactive translation prediction", Machine Translation, 33(3), pp.135~154 (2019)
  20. "MT evaluation: Human measures and assessment methods" (2013)[URL]
  21. "시스트란, 인공지능 고전문헌 자동 번역 시스템 구축" (2018), 블로터뉴스[URL]
  22. "네이버 번역기, 어디까지 왔니?" (2015), 블로터뉴스[URL]
  23. "카카오가 뒤늦게 번역서비스에 뛰어든 까닭은?" (2018), 블로터뉴스[URL]

관련 논문AI추천

이 간행물의 다른 논문 (7건)